Conference Paper

An Alignment Algorithm Using Belief Propagation and a Structure-Based Distortion Model.

DOI: 10.3115/1609067.1609085 Conference: EACL 2009, 12th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference, March 30 - April3, 2009, Athens, Greece
Source: DBLP


In this paper, we first demonstrate the in- terest of the Loopy Belief Propagation al- gorithm to train and use a simple align- ment model where the expected marginal values needed for an efficient EM-training are not easily computable. We then im- prove this model with a distortion model based on structure conservation.

Full-text preview

Available from:
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We study graphical modeling in the case of string- valued random variables. Whereas a weighted finite-state transducer can model the probabilis- tic relationship between two strings, we are inter- ested in building up joint models of three or more strings. This is needed for inflectional paradigms in morphology, cognate modeling or language re- construction, and multiple-string alignment. We propose a Markov Random Field in which each factor (potential function) is a weighted finite-state machine, typically a transducer that evaluates the relationship between just two of the strings. The full joint distribution is then a product of these fac- tors. Though decoding is actually undecidable in general, we can still do efficient joint inference using approximate belief propagation; the nec- essary computations and messages are all finite- state. We demonstrate the methods by jointly pre- dicting morphological forms. 1 Overview
    Full-text · Conference Paper · Jan 2009
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Word alignment plays an important role in many NLP tasks as it indicates the correspondence between words in a parallel text. Although widely used to align large bilingual corpora, generative models are hard to extend to incorporate arbitrary useful linguistic information. This article presents a discriminative framework for word alignment based on a linear model. Within this framework, all knowledge sources are treated as feature functions, which depend on a source language sentence, a target language sentence, and the alignment between them. We describe a number of features that could produce symmetric alignments. Our model is easy to extend and can be optimized with respect to evaluation metrics directly. The model achieves state-of-the-art alignment quality on three word alignment shared tasks for five language pairs with varying divergence and richness of resources. We further show that our approach improves translation performance for various statistical machine translation systems.
    Full-text · Article · Sep 2010 · Computational Linguistics
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We introduce a discriminatively trained, globally normalized, log-linear variant of the lexical translation models proposed by Brown et al. (1993). In our model, arbitrary, non-independent features may be freely incorporated, thereby overcoming the inherent limitation of generative models, which require that features be sensitive to the conditional independencies of the generative process. However, unlike previous work on discriminative modeling of word alignment (which also permits the use of arbitrary features), the parameters in our models are learned from unannotated parallel sentences, rather than from supervised word alignments. Using a variety of intrinsic and extrinsic measures, including translation performance, we show our model yields better alignments than generative baselines in a number of language pairs.
    Preview · Conference Paper · Jan 2011
Show more